Abstract
Word graphs are directed acyclic graphs where each edge is labeled with a word and a score, and each node is labeled with a point in time. Word graphs form an efficient feedforward interface between continuous-speech recognition and linguistic processors. Word graphs with high coverage and modest graph densities can be generated with a computational load comparable with bigram best-sentence recognition. Results on word graph error rates and word graph densities are presented for the ASL (Architecture Speech/Language) benchmark test.

This publication has 5 references indexed in Scilit: